Footballcharts Mcp

io.github.ddevetak由 GitHub 帳號 ddevetak 發布v0.5.0更新於 Nov 2, 2026

Tables, results, fixtures, goal timing, season projections: 93 football leagues incl. lower tiers

已驗證Streamable HTTP可網頁執行位置與生活資料與分析

概覽

AI 產生的概覽

唯讀足球資料伺服器:提供 93 個以上聯賽(含低階聯賽)的積分榜、賽果、賽程、進球時段與模型機率。

可以做什麼
  • 查詢聯賽清單與賽季格式,讀取含預期積分與運氣分類的積分榜
  • 取得已結束比賽的賽果與即將進行的賽程及模型校準機率
  • 依 slug 檢視單場比賽,含球隊評分與進球時段直方圖
  • 取得以每日蒙地卡羅模擬為基礎的賽季預測(奪冠、前四、後三名機率)
  • 檢視單一球隊的賽季比賽紀錄、每 15 分鐘進球分布與首球分布
  • 核對模型的公開校準紀錄(命中率、Brier 分數、可靠度分桶)
適用情境
適合讓助理回答各國足球聯賽(含低階與女子聯賽)的問題:積分榜、近況、進球型態、賽程機率與賽季走勢,並附公開的預測準確度紀錄,而非投注建議。
執行需求
可作為遠端託管端點使用,也可透過 npx 以本機 npm 套件執行(需 Node.js)。不需金鑰:無金鑰方案每 IP 每日 100 次請求。選用的免費金鑰可透過 FC_API_KEY 環境變數、連接器網址或 Authorization 標頭提供,額度提高至每日 200 次。需要能連線至 football-charts.com 的 API。
安裝前請注意
選用的 FC_API_KEY 是僅顯示一次的金鑰;在以網址為基礎的連接器設定中,金鑰會出現在網址內,應將該網址視為敏感資訊。工具請求(聯賽鍵、球隊名稱、賽季)會經 HTTPS 傳送至 football-charts.com,並依 IP 限流。資料可免費供個人與研究使用但須標註來源;不得轉售,付費方案的商業使用須聯絡提供者。機率來自公開基準模型,不構成投注建議。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Footballcharts Mcp,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.ddevetak%2Ffootballcharts-mcp/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "footballcharts": {
      "type": "http",
      "url": "https://mcp.football-charts.com/mcp"
    }
  }
}

README

Football data MCP server — 98 leagues, lower divisions included (Football Charts)

[npm] [license] [MCP registry]

English · 简体中文 (Simplified Chinese)

Give your AI assistant football data for 98 leagues (across 44 countries) — including the lower divisions other sources skip: tables, results, fixtures, goal timing, a public baseline model and Monte Carlo season projections from football-charts.com.

FC publishes probabilities and a public calibration record — not betting tips. Every model probability is published before kickoff and scored after; the get_track_record tool returns that record (hit rate, Brier score, reliability buckets).

No key needed

Every tool works without an API key at 100 requests/day per IP (20/min). A free key, for personal use, lifts that to 200/day, 60/min (all keys on one email address count together) — get one in seconds:

bash
curl -X POST https://footballcharts-backend.onrender.com/api/v1/keys/register/ \  -H 'Content-Type: application/json' \  -d '{"email":"[email protected]"}'

The key (fc_...) is shown once — store it. Both tiers: all 98 leagues (top and lower divisions, women's leagues), current + previous season, model probabilities and daily 10,000-run Monte Carlo projections, no betting odds (the historical odds archive is a paid dataset at football-charts.com/data).

Use it on claude.ai (web or mobile) — nothing to install

Settings → Connectors → Add custom connector, then paste:

https://mcp.football-charts.com/mcp

That is the keyless tier. With a key, paste https://mcp.football-charts.com/fc_your_key_here/mcp instead (a connector field accepts only a URL, so the key travels in it; keys are read-only, free and replaceable). Clients that can send headers use POST https://mcp.football-charts.com/mcp with Authorization: Bearer fc_….

Use with Claude Desktop — one-click extension

Download footballcharts-mcp-<version>.mcpb from the latest release and open it; Claude Desktop installs it. The API key field can stay empty.

Use with Claude Desktop — manual config

claude_desktop_config.json (FC_API_KEY is optional since 0.4.0):

json
{  "mcpServers": {    "football-charts": {      "command": "npx",      "args": ["-y", "footballcharts-mcp"],      "env": { "FC_API_KEY": "fc_your_key_here" }    }  }}

Use with Claude Code

bash
claude mcp add football-charts -e FC_API_KEY=fc_your_key_here -- npx -y footballcharts-mcp

Tools

Ten read-only tools. Each description says what the tool returns.

tooluse it for
about_football_chartsSummary of the source: leagues covered, what it does not hold, league-key and season formats, how to read the probabilities.
list_leaguesEvery league covered (98 across 44 countries) with its key, country and seasons available.
get_league_tableStandings for one league season with form, expected points and a luck category; view=luck or goals for alternative rankings.
get_resultsFinished matches of one league season with full-time and half-time scores and first-goal minute; filter by team, keep the latest N with last.
get_fixturesUpcoming matches of one league with the model's calibrated probabilities.
get_matchOne match in full, by slug: model probabilities, team ratings and goal-timing histograms.
get_season_projectionTitle, top-four and bottom-three probabilities and points ranges from 10,000 simulations, refreshed daily.
get_teamOne team's season: table row, match log, goals per 15-minute period and first-goal distribution.
get_goal_timingGoals per 15-minute period for every team in a league season, with peak periods and league totals; pass team for one team.
get_track_recordThe model's public calibration record: hit rate, Brier score and reliability buckets.

The model is a public baseline (Dixon-Coles). It is calibrated, and get_track_record shows how well; it does not beat the bookmaker market. Per-bookmaker opening and closing odds for 91 leagues, 2020 onward, are a paid dataset at football-charts.com/data.

Changelog

  • 0.6.0 — every answer links the football-charts.com page with the same data (source_url); get_track_record returns a calibration record (hit rate, Brier score, reliability buckets); descriptions say what each tool returns, with no instructions to the model, and each tool's title is also in annotations.title; outputs drop the site-only fields roi_*, profit_* and gates; get_season_projection explains a missing projection instead of failing output validation. Same ten tools and arguments.
  • 0.5.0 — every tool has an outputSchema and returns structuredContent; descriptions rewritten from the consumer side (purpose → when to use a sibling instead → one example); get_match drops storage internals. The tool list is ~6k tokens (was ~3k) — the schemas are the cost. Two deliberate choices: list_leagues keeps its list_ prefix because it enumerates everything rather than fetching one thing, and league stays a free string rather than an enum of the 93 keys (an enum would add ~700 tokens to every tool; list_leagues resolves a name in one call). Schema leaves are untyped so that an unexpected null never fails a call; the field types are what the API returns (numbers for counts and probabilities, ISO dates, 'home:away' score strings).
  • 0.4.1 — registry entry declares the hosted endpoint (remotes) so connector directories list it; get_results ordering wording clarified (chronological, last=N keeps the latest N).
  • 0.4.0 — a key is optional: the API serves keyless callers at 300/day per IP (20/min) and its 429 says how to get a free key; about and list_leagues guidance updated; MCPB desktop-extension bundle (manifest.json, icon); registry isRequired: false for FC_API_KEY.
  • 0.3.0 — descriptions rewritten for the model (when / returns / example); new about_football_charts orientation tool (keyless); get_rankings folded into get_league_table via view; get_goal_timing gains a team filter and peak_bins guidance; one structured log line per tool call on stderr (tool, ok, ms, key prefix — never arguments).
  • 0.2.0 — hosted Streamable HTTP transport, read-only annotations, key accepted from header, path or query for registry gateways.

Things to ask

  • "How does the Allsvenskan title race look after this weekend?"
  • "When does Flamengo usually score — early or late?"
  • "Show me the K League table, and who's overperforming what the market expected."
  • "Which team in Serie B hasn't conceded in the first 15 minutes?"
  • "What is Football Charts' actual prediction track record this season?"

Configuration

Env varDefaultPurpose
FC_API_KEY— (required)Your API key
FC_API_BASEFC production APIOverride for self-hosted/testing

Privacy Policy

This extension sends your tool requests (league keys, team names, seasons — never your conversation) to football-charts.com's API over HTTPS. Requests are rate-limited per IP; if you configure an API key, the key identifies your account and its usage is counted per key. No conversation content is stored. Football Charts' privacy policy: https://www.football-charts.com/privacy. Questions: [email protected].

Terms

Free for personal and research use with attribution ("Data by football-charts.com"). No resale of the data. Commercial use of the paid tier: [email protected].

License

MIT (server code only). The data served by the football-charts.com API remains © football-charts.com, provided under the terms at https://www.football-charts.com/developers.

Claude Code plugin

This repository is also a Claude Code plugin (plugins/football-charts/). It adds the hosted MCP server above (no key needed) and the football-data skill:

/plugin install football-charts --marketplace ddevetak/footballcharts-mcp

Cursor plugin

This repository is also a Cursor plugin (.cursor-plugin/plugin.json). It adds the hosted MCP server above (no key needed) and a football-data skill that explains the tools and the REST API. To try it locally, copy the repository to ~/.cursor/plugins/local/football-charts, reload Cursor, and check Customize for the Football Charts MCP server and skill.

來源:README.md,提交 bef9108

工具

10

about_football_charts

About this source

Returns a summary of the football-charts.com source: the leagues and data it covers (93 leagues, including lower divisions), what it does not hold (live scores, player data, bookmaker odds), the league-key and season-string formats, how the model probabilities are produced, and the free-tier limits. No parameters.

無需輸入參數。

list_leagues

List leagues

Returns every league covered (93 across 42 countries) with its league key, display name, country and the seasons available, newest first. Other tools take these league keys and season strings. Season format depends on the competition: '2026-2027' for winter-calendar leagues, '2026' for summer-calendar leagues. No parameters.

無需輸入參數。

get_league_table

League table

Returns the standings of one league season: one row per team with position, played, wins, draws, losses, goals, points and last-five form, plus expected points and a luck category (how far results run ahead of or behind the underlying performance). view='luck' orders the same rows by over- or under-performance and view='goals' by goals scored; the default orders by points. Without a season, returns the current season.

輸入參數viewleague必填season

get_results

Match results

Returns the finished matches of one league season in chronological order: date, teams, full-time and half-time score, first-goal minute and a goalless flag. team keeps the matches where either side's name contains the given text (case-insensitive); last=N keeps only the N most recent matches. Contains no odds.

輸入參數lastteamleague必填season

get_fixtures

Upcoming fixtures

Returns the upcoming matches of one league, earliest first: kick-off date and time, teams, a match slug, and the model's calibrated probabilities (home and away win, over/under goal lines, both teams to score, half-time lines; the draw probability is 1 - home - away) with team attack and defence ratings. The probabilities come from a baseline statistical model of past results (no injuries, motivation or weather) and are not bookmaker prices.

輸入參數league必填

get_match

Match detail

Returns one match in full, identified by its slug ('country/league-slug/YYYY-MM-DD-home-vs-away', as listed in the slug field of upcoming fixtures): the complete model probability block (calibrated and raw), team ratings, first-goal-time histograms for both sides, recent form and, once played, the score, half-time score and status.

輸入參數slug必填

get_season_projection

Season projection

Returns how one league's current season is projected to finish, from 10,000 Monte Carlo simulations refreshed daily: for each team the probabilities of winning the title, finishing in the top four and finishing in the bottom three, current points, mean final points, a 10th-90th percentile points range, a finishing-position matrix, and the change since the previous run. Covers the current season only; returns a note when no projection exists for the league yet.

輸入參數league必填

get_team

Team page

Returns one team's season in one league: its table row (with expected points and luck category), the full match log (date, opponent, home or away, score, half-time score, first-goal minute, outcome), goals per 15-minute period, the first-goal distribution, and season averages of match statistics (shots, shots on target, possession, corners, xG) where the league has them. team is a lower-case slug with hyphens, e.g. 'arsenal' or 'manchester-city'.

輸入參數team必填league必填season

get_goal_timing

Goal timing

Returns goals per 15-minute period (0-15 to 90+) for every team in one league season, with each team's peak period or periods (ties are listed together), share of late goals and share of first-half goals, plus league totals and the league's most active period. team limits the result to teams whose name contains the given text.

輸入參數teamleague必填season

get_track_record

Model calibration record

Returns the public calibration record of the model: every probability published before kick-off and scored after the result, with count, hit rate, Brier score and reliability buckets (predicted probability against observed frequency), overall and by question type (match result, total goals over 2.5 and 3.5, half-time goals over 1.5, both teams to score), plus the 50 most recent scored predictions. Misses are included. days sets the lookback window (default 90).

輸入參數days

版本歷史

1
  1. v0.5.0最新Sep 16, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分